‘Copper’s time has run out’: Nvidia, AMD and TSMC have invested millions in a startup which may hold the key to faster chip connectivity to quench AI’s thirst for bytes

0
2


  • Ayar Labs is valued at $1 billion and is at the cutting edge of silicon photonics
  • The firm has raised money from a flurry of investors including Intel and Global Foundries
  • It says copper has almost reached its physical limitations for chip interconnections, and now it wants to see what is next

The rapid expansion of AI has brought unprecedented challenges to data movement within AI infrastructure, in particular for traditional copper interconnects, once sufficient for data transfer, but which now struggle to meet the demands of increasingly complex AI models.

This bottleneck has led to inefficiencies in compute performance, energy consumption, and overall scalability, and addressing these issues is crucial as AI adoption continues to grow across industries, requiring a more efficient solution for managing the massive data flows demanded by AI training and inference.

LEAVE A REPLY

Please enter your comment!
Please enter your name here